https://github.com/KonH/StableDiffusionUnityTools

Editor utility to generate assets in Unity Editor via self-hosted & managed Stable Diffusion installations
https://github.com/KonH/StableDiffusionUnityTools

game-development image-generation stable-diffusion unity unity-editor unity3d

Last synced: 3 months ago
JSON representation

Editor utility to generate assets in Unity Editor via self-hosted & managed Stable Diffusion installations

• Host: GitHub
• URL: https://github.com/KonH/StableDiffusionUnityTools
• Owner: KonH
• License: mit
• Created: 2023-01-14T08:55:42.000Z (over 1 year ago)
• Default Branch: master
• Last Pushed: 2023-01-14T13:52:16.000Z (over 1 year ago)
• Last Synced: 2024-01-17T09:47:32.357Z (5 months ago)
• Topics: game-development, image-generation, stable-diffusion, unity, unity-editor, unity3d
• Language: C#
• Homepage:
• Size: 198 KB
• Stars: 41
• Watchers: 3
• Forks: 4
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Lists

• awesome-unity-open-source-on-github - StableDiffusionUnityTools - Editor assets generation via Stable Diffusion (Design)
• awesome-unity3d - StableDiffusionUnityTools - Editor assets generation via Stable Diffusion (Open Source Repositories / Art Tools)
• awesome-opensource-unity - StableDiffusionUnityTools - Editor assets generation via Stable Diffusion. (Open Source Packages / AI Tools)

README

        
# Stable Diffusion Unity Tools

## Summary

Editor utility to generate assets in Unity Editor via self-hosted & managed Stable Diffusion installations

## Installation

1) Setup Stable Diffusion on your local machine - https://github.com/CompVis/stable-diffusion (skip if you will use managed services)

2) Add package in Packages/manifest.json:

   ```

    "com.konh.stable-diffusion-unity-tools": "https://github.com/KonH/StableDiffusionUnityTools.git?path=Packages/com.konh.stable-diffusion-unity-tools"

   ```

3) Click **SD Tools/Setup**, it creates settings file


![](Images/setup.png)

4) Open settings at **Edit/Project Settings/Stable Diffusion** and configure:

   - **Command** - command to execute stable diffusion:

      - Should contain required placeholders: `$PROMPT` for generation prompt, `$OUT_DIR` for destination directory, `$WIDTH` and `$HEIGHT` for image dimensions (these arguments assigned at generation process)

      - Could be multiline for better usability, line breaks are ignored

      - Windows WSL example (in that case paths should be related to Linux file system): `wsl

        --cd "linux-mnt-path-to-stable-diffusion"

        python3 scripts/txt2img.py

        --prompt "$PROMPT" --plms --n_samples 1 --n_iter 1 --outdir "outputs/txt2img-custom/$GUID"`

      - If you want to use managed service - write custom script which communicate with it and store results on file system in txt2img.py compatible format

   - **ResultPath** - full path to directory with generated files on local file system (in case of WSL - Windows host machine)

![](Images/project_settings.png)

5) Additionally, you could add **Assets/StableDiffusionUnityTools** to .gitignore (it's related to current machine, unfortunately we can't use UserSettings for that)

## Asset file generation

Now you can use **SD Tools/Generate Image** to generate images, it provide you ability to tweak settings for next generation:

 - Required settings: **Prompt**, **Directory**, **Width**, **Height**

 - Optional settings: **Name** (if not assigned, GUID is used)

![](Images/generate_window.png)

When generation finished, you will see result in given directory

![](Images/generate_result.png)